Park energy consumption equipment energy-saving control system based on Internet of Things technology

Abstract

The invention relates to the technical field of energy-saving control, in particular to a park energy consumption equipment energy-saving control system based on the Internet of Things technology, which comprises an operation state monitoring module, an energy consumption distribution analysis module, a regional load optimization module, an energy consumption abnormity monitoring module, a fault association module and a signal feedback optimization module. According to the method, the execution efficiency and the power utilization rate of the task are improved through real-time data acquisition of the operation power value and the environment temperature of the energy consumption equipment in combination with time-interval division and arrangement, and the abnormal characteristics are captured through analysis of the fluctuation amplitude and the power offset range for energy consumption abnormity monitoring. The fault propagation path and association strength between the devices are determined, the accuracy of linkage fault positioning between the devices is improved, the adjustment value and the device linkage relation data are verified by optimizing signal feedback control, the control efficiency and the refinement degree of load scheduling are enhanced, and the accuracy of linkage fault positioning between the devices is improved. And the real-time monitoring, dynamic optimization and efficient feedback capabilities under data driving are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving control technology, and in particular to an energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology. Background Art

[0002] The field of energy-saving control technology is mainly committed to achieving efficient management of various energy-consuming equipment by optimizing energy utilization methods and control strategies, thereby reducing energy consumption and operating costs. This field includes hardware equipment, software systems and multi-device collaborative control technology, and is applied to scenarios such as industry, commercial parks, homes and public facilities. The core content involves technologies such as real-time monitoring of energy consumption, energy distribution optimization, load regulation, equipment operation status prediction and intelligent control, aiming to improve energy efficiency, reduce energy waste and achieve sustainable development goals.

[0003] Through the Internet of Things technology, the energy-consuming equipment in the park can be interconnected, the energy consumption data of the equipment can be collected, transmitted and analyzed, and the operation of the equipment can be optimized and managed using intelligent control strategies to achieve the purpose of reducing energy consumption and improving energy utilization efficiency. The system is widely used in scenarios such as industrial parks, commercial complexes and residential communities, and helps to achieve the overall energy-saving and efficiency-enhancing goals of the park.

[0004] Most energy management technologies focus on data collection and analysis of a single device, ignoring the complexity of load coordination and correlation between devices. The identification of abnormal energy consumption behavior mostly relies on fixed threshold judgments, and fails to extract complex fluctuation characteristics, resulting in omissions or misjudgments of potential anomalies. They lack dynamic adjustment capabilities based on real-time data, which can easily lead to unbalanced regional resource allocation. They fail to analyze signal conflicts or redundant relationships between devices, resulting in inefficient feedback control, affecting the accuracy and overall performance of energy optimization management, and causing problems such as increased energy costs, reduced equipment operating efficiency, and unreasonable resource allocation. Summary of the invention

[0005] In order to solve the problems that most energy consumption management technologies in the prior art focus on data collection and analysis of a single device, ignore the complexity of load coordination and correlation between devices, and the identification of abnormal energy consumption behavior mostly relies on fixed threshold judgment, and fails to extract complex fluctuation characteristics, resulting in omission or misjudgment of potential abnormalities, lack of dynamic adjustment capabilities based on real-time data, and easily lead to unbalanced regional resource allocation, and fail to analyze signal conflicts or redundant relationships between devices, resulting in low feedback control efficiency, affecting the accuracy and overall performance of energy consumption optimization management, and causing technical problems such as increased energy consumption costs, reduced equipment operating efficiency and unreasonable resource allocation, the embodiment of the present invention provides an energy-saving control system for campus energy-consuming equipment based on Internet of Things technology. The technical solution is as follows: On the one hand, an energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology is provided, including: The operation status monitoring module collects the operating power value and ambient temperature of each energy-consuming device, timestamps the collected data through the IoT terminal, calculates the load level of the energy-consuming device in multiple time periods, and divides the time period by time according to the load level of the device to obtain the load data for each time period; The energy consumption distribution analysis module collects the operating power value and time distribution data of the energy-consuming equipment through the IoT terminal based on the load data in each period, performs correlation calculation on the power value and time distribution data of multiple segments, analyzes the total operating power and the corresponding time distribution characteristics in the task window, and reorders the segments according to the task priority to obtain the task power priority information; The regional load optimization module is based on the task power priority information and the distribution of IoT regional nodes, and counts the ratio of each segment load in the task window, recalculates the segment load data in the task window, extracts the distribution value of the load between regions, and performs a balanced comparison of the distribution value of each region to obtain a balanced load distribution value; The energy consumption abnormality monitoring module monitors the time series data of the operating power value of the energy-consuming equipment in real time based on the balanced load distribution value, identifies the load fluctuation point in the time series, determines whether there is abnormal fluctuation in the power value by calculating the fluctuation amplitude and the power offset range, and performs segmented statistics on the abnormal fluctuation points according to the offset amplitude and time range to obtain an abnormal fluctuation feature table; The fault association module identifies the load linkage data and fluctuation frequency of abnormal energy-consuming equipment based on the abnormal fluctuation feature table, analyzes the load linkage relationship between equipment, identifies the strong and weak correlations between equipment by calculating the linkage dependency value, and sorts them according to the impact on the equipment linkage relationship to obtain the equipment linkage fault impact result; The signal feedback optimization module extracts the load distribution adjustment value and the linkage relationship data between the devices based on the impact results of the equipment linkage failure, cross-checks the adjustment value and the linkage relationship, identifies the conflict or redundancy of the equipment linkage relationship, and optimizes the adjustment signal and time allocation data to obtain the control signal optimization result.

[0006] On the other hand, the time period load data includes segmented operating power values, segmented ambient temperature data, and equipment load level grouping information; the task power priority information includes task power allocation values, time period task distribution characteristics, and task priority sorting data; the balanced load distribution value includes regional load distribution ratios, inter-regional load balancing results, and segmented load distribution adjustment data; the abnormal fluctuation feature table includes load fluctuation amplitude characteristics, abnormal time segment data, and abnormal point offset feature information; the equipment linkage fault impact results include equipment linkage dependency, inter-equipment linkage strength relationship, and linkage fault sorting data; the control signal optimization results include adjusted signal allocation rules, optimized time allocation table, and inter-equipment signal linkage relationship table.

[0007] On the other hand, the operation status monitoring module includes a data acquisition submodule, a time marking and grouping submodule, and a load data sorting submodule; The data acquisition submodule is based on the energy-consuming equipment in the park. It collects the operating power value and ambient temperature data of each energy-consuming equipment through the operating power sensor and ambient temperature sensor to obtain the operating power and ambient data set; The time marking and grouping submodule associates the data timestamp based on the operating power and environment data set, reads the timestamp field in the data, compares it with the standard time index, groups the data according to the time dimension, and obtains the time series marking and grouping data; The load data sorting submodule calculates based on the time series annotation and grouping data according to the load level of the energy-consuming equipment, divides it into time periods, determines the peak and average of the operating power in the data, and obtains the load data for each time period.

[0008] On the other hand, the energy consumption distribution analysis module includes a power data acquisition submodule, a power distribution characteristic analysis submodule, and a task power sorting submodule; The power data acquisition submodule is based on the load data in each period, and the operating power value and time distribution data of the energy-consuming equipment collected by the IoT terminal, combined with the identification information of the energy-consuming equipment, identifies key feature points, including power peak value, valley value and stable interval, to obtain power time distribution data; The power distribution characteristic analysis submodule analyzes the power value and time distribution data in each time period based on the power time distribution data, calculates the cumulative value of the operating power in chronological order, and then performs distribution characteristic statistics on multiple segments of data in combination with time tags to obtain power distribution characteristic information; The task power sorting submodule determines the power distribution characteristic data in the task window based on the power distribution characteristic information, compares the operating power demand and time period distribution according to the task priority, adjusts the time period sequence and power distribution, and obtains the task power priority information.

[0009] On the other hand, the identification information of the energy-consuming device is combined to check the integrity of the operating power value and time distribution data record, according to the formula: ; Calculate the operating power value integrity determination index I; in, Represents the measured power value of the energy-consuming device collected by the IoT terminal in time period t, Represents the reference operating power value of the energy-consuming equipment, represents the smoothness coefficient of power distribution within the time period, and Respectively represent the starting point and ending point of the time distribution of the power recording data, represents the total number of time points in the period, It is the time unit of integration and defines the continuity of the integral calculation.

[0010] On the other hand, the regional load optimization module includes a segment load statistics submodule, a regional load distribution submodule, and a load balancing comparison submodule; The segment load statistics submodule analyzes the segment load data according to the time division based on the task power priority information and the segment load data in the task window, calculates the ratio of each segment operation power, determines the proportional relationship of the segment load, and obtains the segment load ratio data; The regional load distribution submodule identifies the distribution node data of each region based on the segment load ratio data and the regional node distribution of the Internet of Things, compares the segment load ratio with the regional node capacity, calculates the redistributed load value node by node, and classifies the segment load value by region to obtain the regional distribution load value; The load balancing comparison submodule allocates load values ​​based on the area, analyzes regional resource distribution and task requirements, groups and calculates the load values ​​of the area, determines unbalanced nodes with regional load differences based on the load values, adjusts the node load relationship, and obtains a balanced load distribution value.

[0011] On the other hand, the comparison between the segment load ratio and the regional node capacity is performed to calculate the redistributed load value node by node, according to the formula: ; Calculate the redistributed load value for each node ; in, Representative Node The original segment load value, Representative Node The capacity, Represents the number of all nodes in the region, Represents the number of all nodes in the segment load data.

[0012] On the other hand, the energy consumption abnormality monitoring module includes a load fluctuation monitoring submodule, an abnormal power determination submodule, and a fluctuation characteristic statistics submodule; The load fluctuation monitoring submodule monitors the change data of each period in sections based on the balanced load distribution value, identifies the load change point, and classifies the time position and power difference of the change point to obtain the load fluctuation point information; The abnormal power determination submodule analyzes the amplitude and offset range of power fluctuation based on the load fluctuation point information, compares the fluctuation amplitude value with the offset range limit, and screens abnormal data to obtain abnormal fluctuation point information; The fluctuation feature statistics submodule identifies the power offset value within the time range based on the abnormal fluctuation point information, the offset amplitude and time range of the abnormal fluctuation point, and analyzes the fluctuation features in each segment to obtain an abnormal fluctuation feature table.

[0013] On the other hand, the fault association module includes a load linkage identification submodule, an equipment correlation calculation submodule, and a linkage impact sorting submodule; The load linkage identification submodule calculates the fluctuation frequency in the time series based on the abnormal fluctuation feature table, compares the load changes of multiple energy-consuming devices, identifies the corresponding relationship between the time point and the fluctuation amplitude, marks the linkage features of the energy-consuming devices, and obtains the device linkage data; The device correlation calculation submodule analyzes the load linkage relationship of the energy-consuming equipment based on the device linkage data, calculates the dependency value of the load change value of the energy-consuming equipment and the linkage time, and obtains the device correlation strength value; The linkage impact sorting submodule sorts the impact values ​​based on the equipment association strength value and the impact values ​​of the linkage relationship of the energy-consuming equipment in combination with the sorting rules, adjusts the association order of the energy-consuming equipment, filters the conflicting impact values, and obtains the equipment linkage fault impact result.

[0014] On the other hand, the signal feedback optimization module includes a load adjustment value extraction submodule, a linkage relationship verification submodule, and a signal optimization calculation submodule; The load adjustment value extraction submodule analyzes the corresponding rules between the load adjustment value and the linkage relationship based on the equipment linkage fault impact result, analyzes the linkage correlation and state fluctuation amplitude between the equipment, determines the linkage equipment relationship corresponding to the adjustment value, and obtains the load adjustment relationship data; The linkage relationship verification submodule verifies the dependency between the adjustment value and the device linkage relationship based on the load adjustment relationship data, extracts the conflict points of the device linkage, analyzes the time dependency value and the linkage relationship of the conflict point, marks the conflict characteristics, and re-associates the adjustment value with the linkage relationship to obtain the adjustment conflict dependency characteristic result; The signal optimization calculation submodule adjusts the signal and time allocation data based on the adjustment conflict dependency characteristic results, combines the time interval of the adjustment signal with the device priority, analyzes the mutual influence of the time sequence and the interactive regulation between devices, recalculates and reconstructs the signal time series, and obtains the control signal optimization result.

[0015] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: By collecting real-time data on the operating power value and ambient temperature of energy-consuming equipment, combined with time period division and organization, the execution efficiency and power utilization rate of the task are improved. For abnormal energy consumption monitoring, the abnormal characteristics are captured by analyzing the fluctuation amplitude and power offset range, providing data support for correlation analysis and accurate diagnosis. In the linkage fault analysis, the fault propagation path and correlation strength between devices are determined based on the load linkage relationship and dependency value calculation, which improves the accuracy of linkage fault location between devices. By optimizing signal feedback control, the adjustment value is verified with the equipment linkage relationship data, which enhances the control efficiency and the refinement of load scheduling, and strengthens the real-time monitoring, dynamic optimization and efficient feedback capabilities driven by data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of the system of the present invention; Figure 2 It is a schematic diagram of the system framework of the present invention; Figure 3 This is a flow chart of the operating status monitoring module of the present invention; Figure 4 It is a flow chart of the energy consumption distribution analysis module of the present invention; Figure 5 A flow chart of a regional load optimization module of the present invention; Figure 6 This is a flow chart of the energy consumption abnormality monitoring module of the present invention; Figure 7 It is a flow chart of the fault association module of the present invention; Figure 8 This is a flow chart of the signal feedback optimization module of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0021] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be written in non-subscript form such as W1. When the difference is not emphasized, the meaning is the same.

[0022] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0023] The embodiment of the present invention provides an energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology, such as Figure 1 As shown, the system includes: The operation status monitoring module collects the operating power value and ambient temperature of each energy-consuming device, timestamps the collected data through the IoT terminal, calculates the load level of the energy-consuming device in multiple time periods, and divides the time period by time according to the load level of the device to obtain the load data for each time period; The energy consumption distribution analysis module collects the operating power value and time distribution data of energy-consuming equipment through the IoT terminal based on the load data of each period, performs correlation calculation on the power value and time distribution data of multiple segments, analyzes the total operating power and corresponding time distribution characteristics within the task window, and reorders the segments according to the task priority to obtain the task power priority information; The regional load optimization module is based on the task power priority information and the regional node distribution of the Internet of Things. It counts the ratio of each segment load in the task window, recalculates the segment load data in the task window, extracts the distribution value of the load between regions, and compares the distribution value of each region to obtain the balanced load distribution value. The energy consumption abnormality monitoring module monitors the time series data of the operating power value of energy-consuming equipment in real time based on the balanced load distribution value, identifies the load fluctuation points in the time series, and determines whether there is abnormal fluctuation in the power value by calculating the fluctuation amplitude and power offset range. The abnormal fluctuation points are segmented and counted according to the offset amplitude and time range to obtain the abnormal fluctuation feature table; The fault association module identifies the load linkage data and fluctuation frequency of abnormal energy-consuming equipment based on the abnormal fluctuation feature table, analyzes the load linkage relationship between equipment, identifies the strong and weak correlations between equipment by calculating the linkage dependency value, and sorts them according to the impact on the equipment linkage relationship to obtain the impact results of equipment linkage faults; The signal feedback optimization module extracts the load distribution adjustment value and the linkage relationship data between devices based on the impact of equipment linkage failure, cross-checks the adjustment value and the linkage relationship, identifies the conflict or redundancy of the equipment linkage relationship, and optimizes the adjustment signal and time allocation data to obtain the control signal optimization result.

[0024] The load data for each time period includes the segmented operating power value, the segmented ambient temperature data, and the equipment load level grouping information. The task power priority information includes the task power allocation value, the time period task distribution characteristics, and the task priority sorting data. The balanced load distribution value includes the regional load distribution ratio, the inter-regional load balancing result, and the segmented load distribution adjustment data. The abnormal fluctuation feature table includes the load fluctuation amplitude characteristics, the abnormal time segment data, and the abnormal point offset feature information. The equipment linkage fault impact results include the equipment linkage dependency, the linkage strength relationship between equipment, and the linkage fault sorting data. The control signal optimization results include the adjusted signal allocation rules, the optimized time allocation table, and the signal linkage relationship table between equipment.

[0025] like Figure 2 and Figure 3 As shown, the operation status monitoring module includes a data acquisition submodule, a time marking and grouping submodule, and a load data sorting submodule; The data acquisition submodule is based on the energy-consuming equipment in the park. It collects the operating power value and ambient temperature data of each energy-consuming equipment through the operating power sensor and ambient temperature sensor to obtain the operating power and ambient data set; The equipment operating status data is continuously collected through sensors, and the operating power and ambient temperature data are extracted. During the collection process, the sensor signal is first subjected to voltage standardization, and the equipment operating power signal is synchronously collected according to the preset sampling period. At the same time, the ambient temperature sensor signal is converted into a digital form and the data is recorded. During the collection process, abnormal signal values ​​are eliminated, and signal values ​​where the operating power signal is lower than the set threshold or the ambient temperature signal fluctuates beyond the normal range are eliminated. The linear interpolation method is used to compensate for the intermittently collected signals. After completing the data collection, the collected data is checked for integrity, and the data flag is used to determine the missed or repeated records. The incomplete data records are eliminated and a complete set of operating power and ambient temperature data is generated.

[0026] The time labeling and grouping submodule associates the data timestamps based on the operating power and environment data set, reads the timestamp field in the data, compares it with the standard time index, groups the data according to the time dimension, and obtains the time series labeling and grouping data; Perform association correction on the timestamp of each data record, compare the timestamp with the reference time in the standard time index table, calculate the error value between the record timestamp and the reference time, and classify them according to the size of the error. Set the records that exceed the error range as invalid records, and divide the remaining valid records into continuous time groups according to the time interval. Each group records the data within a time period. For each group of records, calculate the start time and end time of its time period. At the same time, use the number of data in the time period and the time interval to verify the continuity of the time grouping, so that the data distribution of each time period is complete, and generate time series annotations and grouped data.

[0027] The load data sorting submodule calculates based on the time series annotation and grouping data according to the load level of the energy-consuming equipment, divides it into time periods, determines the peak and average values ​​of the operating power in the data, and obtains the load data for each time period; First, the power values ​​in each group of segmented data are sorted, and the values ​​are extracted as peak values. At the same time, the arithmetic mean of the power values ​​in the segment is calculated as the mean. For the calculation of the load level, the operating power ratio in the segment is introduced as the reference value of the load level. The load changes in the time period are subdivided, and the load level in the time period is divided into hours. The load adjustment coefficient is set according to the difference between the peak value and the mean value in the segment. The load level estimate is adjusted for the time period with large power fluctuations. After load sorting, the load data of multiple time periods is output to obtain the load data for each time period.

[0028] like Figure 2 and Figure 4 As shown, the energy consumption distribution analysis module includes a power data acquisition submodule, a power distribution characteristic analysis submodule, and a task power sorting submodule; The power data acquisition submodule is based on the load data of each period, and the operating power value and time distribution data of the energy-consuming equipment collected by the IoT terminal, combined with the identification information of the energy-consuming equipment, identifies key feature points, including power peak, valley and stable interval, and obtains power time distribution data; First, the operating power value and timestamp are extracted from the terminal record, and the power value is associated with the corresponding device using the device identification information. The integrity of the timestamp and power value in each data record is checked, the format and continuity of the timestamp field are verified, and abnormal data in the power value record is filtered out by setting a threshold range. The missing data is completed using linear interpolation to ensure that the power data of each device in the entire sampling period is complete. The operating power values ​​are then grouped by hour based on the timestamp, and the start and end time of each group of data is recorded. Each group of segmented data is bound to the device identification to generate a power time distribution data set.

[0029] Combined with the identification information of the energy-consuming equipment, check the integrity of the operating power value and time distribution data records according to the formula: ; Calculate the operating power value integrity determination index I; in, Represents the measured power value of the energy-consuming device collected by the IoT terminal in time period t, Represents the reference operating power value of energy-consuming equipment, which is obtained based on equipment identification information and historical data statistics. The smoothness coefficient of the power distribution within the period is related to the fluctuation degree of the operating power. and Respectively represent the starting point and ending point of the time distribution of the power recording data, represents the total number of time points in the period, It is the time unit of integration and defines the continuity of the integral calculation.

[0030] The power value data of energy-consuming equipment collected by the IoT terminal is constructed For example, the hourly power record of a device during a day is kilowatt; Reference operating power value Obtained based on the historical average value of the device. For example, based on historical data, the reference operating power is kilowatt; Using the absolute error formula Calculate the error value for each period; The calculation is as follows:

[0031] The sum of the error values ​​in each period is: ; Integrate the smoothness of the power distribution within the time period and select (According to the statistical standard setting of actual operating power fluctuation, the greater the fluctuation, the smaller the coefficient), calculate the integral point by point: ; Comprehensive calculation integrity judgment index I: ; The smaller the deviation of the power value, the higher the integrity of the data record, and the result can be used to further analyze power distribution anomalies or complete data records.

[0032] The power distribution characteristic analysis submodule analyzes the power value and time distribution data in each time period based on the power time distribution data, calculates the cumulative value of the operating power in chronological order, and then performs distribution characteristic statistics on multiple segments of data in combination with time tags to obtain power distribution characteristic information; The power value and time record in each time period are extracted, the power value is cumulatively calculated, the timestamp sequence is extracted from the segmented records and sorted in ascending order, the cumulative sum of the power values ​​in each group of data is calculated, and the power value distribution in the time period is counted. The power value in the time period is divided into intervals at fixed intervals, and the number of occurrences of the power value in each interval is counted. The power distribution histogram is formed by combining the cumulative power and interval frequency in the time period. The distribution characteristic information is extracted by analyzing the histogram data points, and finally the power distribution characteristic information in each time period is generated according to the cumulative power and frequency data.

[0033] The task power sorting submodule determines the power distribution characteristic data within the task window based on the power distribution characteristic information, compares the operating power demand and time period distribution according to the task priority, adjusts the time period sequence and power distribution, and obtains the task power priority information; First, determine the time range of the task window, filter the distribution characteristic data according to the time range, extract the cumulative power and power distribution characteristic parameters in each time period, compare the power demand with the task priority in different time periods, classify the task power demand by building a priority sorting table, match high-priority tasks to time periods with stable power distribution, adjust the time period order to optimize the power distribution, re-record the time period information of the task power distribution according to the adjustment results, and output the task power priority information.

[0034] like Figure 2 and Figure 5 As shown, the regional load optimization module includes a segmented load statistics submodule, a regional load distribution submodule, and a load balancing comparison submodule; The segment load statistics submodule analyzes the segment load data according to the time division based on the task power priority information and the segment load data in the task window, calculates the ratio of each segment operation power, determines the proportional relationship of the segment load, and obtains the segment load ratio data; First, each segmented data is filtered in chronological order, the power records in the segment are extracted and their proportion in the entire task window is calculated, and the segmented load ratio is obtained by dividing the cumulative value of the operating power in the segmented data by the total power of the task window. For missing segmented data, the corresponding operating power value is supplemented by interpolation, and the ratio distribution is recalculated. Then, the ratio of the segmented data is normalized to ensure that the segmented load ratio can represent the load ratio relationship in multiple time periods, and generate the segmented load ratio data after the power ratio is normalized.

[0035] The regional load distribution submodule is based on the segment load ratio data and the regional node distribution of the Internet of Things. It identifies the distribution node data of each region, compares the segment load ratio with the regional node capacity, calculates the redistributed load value node by node, and classifies the segment load value by region to obtain the regional distribution load value. Combined with the distribution data of regional nodes of the Internet of Things, the allocation node information of each region is extracted. By matching the power capacity of the regional nodes with the segmented load ratio, the capacity information of multiple nodes is first extracted according to the regional distribution, and the load share of each regional node is calculated. The segmented load ratio is allocated to the power value according to the capacity ratio of the regional node. In the case where the node capacity is insufficient to bear the segmented load, the load is adjusted by distributing it to the nodes in the same region, and then the segmented data is regionally classified according to the adjusted allocation results. Each segmented load record is bound to the corresponding regional node to generate the regional allocated load value.

[0036] Compare the segment load ratio with the regional node capacity, and calculate the redistributed load value node by node, according to the formula: ; Calculate the redistributed load value for each node ; in, Representative Node The original segment load value, Representative Node The capacity, Represents the number of all nodes in the region, Represents the number of all nodes in the segment load data.

[0037] Detailed explanation of the formula and the process of formula calculation and derivation: Segment load value The segment load ratio data is collected node by node through the IoT. For example, the segment load data in a certain area is recorded as kilowatt; Node capacity Collect capacity values ​​based on the capacity distribution of IoT regional nodes, such as kilowatt; Total regional capacity

[0038] Calculate the total capacity of all nodes: ; Segment load sum

[0039] Calculate the sum of the segment loads: ; Redistribution load value calculation The redistributed load value for each node is calculated item by item according to the formula: For Node 1: ; For Node 2: ; For Node 3: ; The redistributed load values ​​are 0.74 kW for node 1, 0.925 kW for node 2, and 1.233 kW for node 3. The results show that by comparing the segment load ratio and node capacity, the load value can be redistributed while maintaining the capacity balance between nodes, optimizing the load distribution in the region and ensuring the rationality and uniformity of load distribution.

[0040] The load balancing comparison submodule allocates load values ​​based on regions, analyzes regional resource distribution and task requirements, calculates regional load values ​​in groups, determines unbalanced nodes with regional load differences based on load values, adjusts node load relationships, and obtains balanced load distribution values; The load difference in each region is calculated by grouping the regional distributed load values ​​by nodes, the load data of each regional node is extracted and its mean is calculated, and the nodes whose load values ​​exceed the regional mean are judged as unbalanced nodes. For unbalanced nodes, the load is redistributed by adjusting the load values ​​of the nodes in the region. For nodes with insufficient load, they are supplemented by reducing the allocated load of the nodes. The adjustment is repeated until the load difference in the region is lower than the preset threshold to obtain a balanced load distribution value.

[0041] like Figure 2 and Figure 6 As shown, the energy consumption abnormality monitoring module includes a load fluctuation monitoring submodule, an abnormal power determination submodule, and a fluctuation characteristic statistics submodule; The load fluctuation monitoring submodule monitors the change data of each period in sections based on the balanced load distribution value, identifies the load change point, and classifies the time position and power difference of the change point to obtain the load fluctuation point information; Determine the time series data of the operating power value of the energy-consuming equipment, divide the time series into hourly segmented data by extracting the power value of each time period in the time series, compare the operating power value of each section with the power value of the adjacent time period, calculate the power change in each time period and record the change point, classify the change point using the time information of the change point, classify the change point according to positive change and negative change, calculate the power difference of the change point, divide the change point into different amplitude levels based on the absolute value interval of the difference, record the time position of the change point and the corresponding power difference, and generate the load fluctuation point information in the segmented record.

[0042] The abnormal power determination submodule analyzes the amplitude and offset range of power fluctuations based on the load fluctuation point information, compares the fluctuation amplitude value with the offset range limit, and screens abnormal data to obtain abnormal fluctuation point information; Analyze the amplitude and offset range of power fluctuations, screen the power difference in the fluctuation points, compare the power fluctuation amplitude with the preset fluctuation amplitude threshold, mark the fluctuation points that exceed the threshold as abnormal points, analyze the time offset range corresponding to the fluctuation points, calculate the time interval between the fluctuation point timestamp and the normal operating power data, compare the time interval with the offset range limit, screen the fluctuation points that exceed the limit as abnormal fluctuation points, and record the power difference and offset range of the abnormal fluctuation points at the same time, and finally output complete abnormal fluctuation point information.

[0043] Analyze the amplitude and offset range of power fluctuations, compare the fluctuation amplitude value with the offset range limit, according to the formula: ; ; ; Calculate the volatility value and offset range values ; in, Representative Node The maximum power value is obtained by detecting the load fluctuation point data. Representative Node The minimum power value is obtained by detecting the load fluctuation point data. Representative Node The average power value is calculated based on the load time series data. Representative Node The reference power value is obtained based on historical operation data or equipment operation standard value statistics.

[0044] Power data acquisition Collection Node The power fluctuation point data within a specific period of time is recorded as; kilowatt; Calculate the maximum and minimum power values; is the maximum value in the collected data, is the minimum value in the collected data: ; Calculate the average power value; Average power value is the arithmetic mean of the collected data: ; in is the total number of points in the recording period. Substitute the data: ; Calculate reference power value; Reference power value Obtained through historical operation records, for example, 14 kilowatts; Calculate the fluctuation range value; According to the formula; ; Substitute the data: ; Calculate the offset range value According to the formula ; Substitute the data: ; The fluctuation amplitude value is 0.659, indicating that the power fluctuation degree is about 65.9% of the average power value. The offset range value is 5 kilowatts, indicating that the power fluctuation deviates from the reference power by an average of 5 kilowatts. These results are used to provide a reference for screening abnormal data points. By comparing with the set fluctuation amplitude and offset range limits, the fluctuation point information of power abnormality is marked.

[0045] The fluctuation feature statistics submodule identifies the power offset value within the time range based on the abnormal fluctuation point information, the offset amplitude and time range of the abnormal fluctuation point, and analyzes the fluctuation features in each segment to obtain the abnormal fluctuation feature table; First, the time range of the abnormal fluctuation point is located from the segmented records, the power data within the time range is analyzed point by point, the cumulative amount of power offset value is calculated, the offset value is classified into different fluctuation categories according to the fluctuation amplitude, and the fluctuation characteristics are classified according to the time range information. The abnormal fluctuation point characteristics in each time period are counted by category, and the characteristic parameter values ​​and time range information are recorded to generate an abnormal fluctuation feature table containing the abnormal fluctuation characteristics of each time period.

[0046] like Figure 2 and Figure 7 As shown, the fault association module includes a load linkage identification submodule, an equipment correlation calculation submodule, and a linkage impact sorting submodule; The load linkage identification submodule calculates the fluctuation frequency in the time series based on the abnormal fluctuation feature table, compares the load changes of multiple energy-consuming devices, identifies the corresponding relationship between the time point and the fluctuation amplitude, marks the linkage features of the energy-consuming devices, and obtains the device linkage data; By counting the frequency of occurrence of fluctuation points in the time series, the fluctuation points of each energy-consuming device are arranged in chronological order, and the number of fluctuation points per unit time is calculated as the fluctuation frequency. At the same time, the power fluctuation data of multiple energy-consuming devices in the same time period are extracted, and the amplitude and direction of power changes are compared. The fluctuation characteristics of multiple devices at the same time point are identified, the difference between the amplitude values ​​of the fluctuation points is calculated, and the linkage characteristics between devices in the time period are marked. The device linkage data is generated by combining the fluctuation amplitude value of each device in the linkage characteristics.

[0047] The equipment correlation calculation submodule analyzes the load linkage relationship of energy-consuming equipment based on equipment linkage data, calculates the dependency value of the load change value of energy-consuming equipment and linkage time, and obtains the equipment correlation strength value; Extract the load change value and corresponding linkage time information of each energy-consuming device. First, calculate the load change value of each energy-consuming device, match the change value with the linkage time point, and use the synchronization of load changes of multiple devices within the linkage time point to calculate the linkage dependency value between devices. Normalize the load change value and the time point dependency value. After normalization, calculate the linkage strength between devices, and correspond the linkage strength to the device identification to generate the correlation strength value of each device. Integrate the strength value with the time series information to form quantitative data of the correlation relationship between devices.

[0048] The linkage impact sorting submodule sorts the impact values ​​based on the strength of the equipment association and the impact values ​​of the linkage relationship of the energy-consuming equipment in combination with the sorting rules, adjusts the association order of the energy-consuming equipment, filters the conflicting impact values, and obtains the impact results of the equipment linkage failure; Extract the linkage relationship and impact value of energy-consuming equipment, count the correlation strength values ​​according to the time series distribution of energy-consuming equipment, and sort the linkage impact values ​​between equipment according to the preset sorting rules. First, extract the correlation strength value and the corresponding time point of each equipment, sum the strength values ​​of the equipment at multiple time points to calculate the total correlation strength, arrange the total correlation strength from high to low according to the sorting rules, and record the linkage impact relationship and sorting results of the equipment, and finally generate the priority information of the linkage impact of energy-consuming equipment.

[0049] According to the impact value of the linkage relationship of energy-consuming equipment, the impact value is sorted in combination with the sorting rules, according to the formula: ; ; ; Computing equipment The linkage relationship impact value ; in, Representative equipment With equipment The correlation strength value is obtained based on the equipment linkage relationship matrix. Representative equipment Energy consumption level, based on monitoring data collection, Representative equipment The operating capacity, Represents the total number of devices in the area. It is the sum of the operating capacities of all devices in the area.

[0050] Detailed explanation of the formula and the process of formula calculation and derivation: Equipment association strength value Obtained through historical data or correlation analysis of equipment linkage relationships For example, the correlation matrix of equipment in a certain area is: ; in It means that the correlation strength between device 1 and device 2 is 0.8; Equipment energy consumption level Based on real-time power monitoring data of the equipment, energy consumption level Collected as: kilowatt; Equipment operating capacity The operating capacity of the equipment is obtained through distributed monitoring of IoT nodes; kilowatt; Total capacity in the area Calculate the total capacity in the area based on the equipment operating capacity: ; Calculate the impact value of device linkage relationship For device 1, the impact value is calculated item by item according to the formula: ; Expand calculation: ; Substitute the data: ; Step-by-step calculation: ; ; The linkage relationship impact value of equipment 1 is 36.001 kilowatts, indicating the degree of its influence on the regional linkage failure. By sorting the impact values ​​of all equipment and adjusting the association order of energy-consuming equipment, the impact results of equipment linkage failure can be obtained more accurately, providing an important reference for optimizing the operation of energy-consuming equipment and fault handling.

[0051] like Figure 2 and Figure 8 As shown, the signal feedback optimization module includes a load adjustment value extraction submodule, a linkage relationship verification submodule, and a signal optimization calculation submodule; The load adjustment value extraction submodule analyzes the corresponding rules between the load adjustment value and the linkage relationship based on the impact of the equipment linkage failure, analyzes the linkage correlation and state fluctuation amplitude between the equipment, determines the linkage equipment relationship corresponding to the adjustment value, and obtains the load adjustment relationship data; Firstly, the device identification and fault time series in the linkage fault impact results are extracted, and the load change values ​​and status fluctuation amplitudes of multiple devices at the linkage time point are extracted. The historical average values ​​of the load change value and the fluctuation amplitude are compared with the associated device information in the historical linkage records, and the correlation between the adjustment value and the device is judged. The adjustment value allocation rule is calculated according to the linkage strength between the devices, and the relationship between each adjustment value and its corresponding linkage device is summarized to form a rule set corresponding to the adjustment value and the device linkage, and generate load adjustment relationship data containing the matching of device relationship and adjustment value.

[0052] The linkage relationship verification submodule verifies the dependency between the adjustment value and the device linkage relationship based on the load adjustment relationship data, extracts the conflict points of the device linkage, analyzes the time dependency value and linkage relationship of the conflict points, marks the conflict characteristics, and re-associates the adjustment value with the linkage relationship to obtain the adjustment conflict dependency characteristic result; By performing linkage conflict analysis on the dependent devices of each adjustment value, firstly extract the device identification and the corresponding time range in the adjustment relationship data, calculate the linkage strength and the adjustment value change rate within the time range, screen the device pairs with conflicts in the dependency relationship, extract the time dependency values ​​of the conflicting devices, analyze the linkage change characteristics within the time period of the conflict point by calculating the change difference of the conflict point within the adjustment value range, mark the device identification, time position and adjustment value difference of the conflict point, and then reallocate the adjustment value to the non-conflicting device linkage relationship to generate the adjustment conflict dependency characteristic result including the conflict characteristics and the adjustment relationship.

[0053] The signal optimization calculation submodule adjusts the signal and time allocation data based on the adjustment conflict dependency characteristic results, combines the time interval of the adjustment signal with the device priority, analyzes the mutual influence of the time sequence and the interactive regulation between devices, recalculates and reconstructs the signal time series, and obtains the control signal optimization result; Extract the time interval and device priority information in the signal adjustment, extract the adjustment signal according to the device priority order within the time interval, analyze the interactive control characteristics between priority devices within the time period, combine the time allocation of the adjustment signal and the correlation between devices, calculate the redistribution rules of the adjustment signal between devices, reconstruct the signal time series, rearrange the time points and the priority order of signal allocation, optimize the signal time series into a distribution result arranged in priority order, output the optimized control signal time series and generate the control signal optimization result.

[0054] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0055] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0056] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0057] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0059] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0062] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0063] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An energy-saving control system for energy-consuming equipment in a park based on Internet of Things technology, characterized in that: The system comprises: The operation status monitoring module collects the operating power value and ambient temperature of each energy-consuming device, timestamps the collected data through the IoT terminal, and divides the data into time periods according to the equipment load level to obtain the load data for each time period; The energy consumption distribution analysis module collects the operating power value and time distribution data of the energy-consuming equipment through the Internet of Things terminal based on the load data in each period, analyzes the total operating power and the corresponding time distribution characteristics in the task window, and obtains the task power priority information; The regional load optimization module is based on the task power priority information and the regional node distribution of the Internet of Things, and counts the ratio relationship of each segment load in the task window, and performs a balanced comparison on the distribution value of each area to obtain a balanced load distribution value; The energy consumption abnormality monitoring module monitors the time series data of the operating power value of the energy-consuming equipment in real time based on the balanced load distribution value, calculates the fluctuation amplitude and the power offset range, and performs segmented statistics on the abnormal fluctuation points according to the offset amplitude and time range to obtain an abnormal fluctuation feature table; The fault association module identifies the load linkage data and fluctuation frequency of abnormal energy-consuming equipment based on the abnormal fluctuation feature table, identifies the strong and weak correlations between equipment by calculating the linkage dependency value, and obtains the impact result of equipment linkage fault; The signal feedback optimization module extracts the load distribution adjustment value and the linkage relationship data between devices based on the impact result of the equipment linkage failure, identifies the conflict or redundancy of the equipment linkage relationship, and optimizes the adjustment signal and time allocation data to obtain the control signal optimization result.

2. According to the energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology in claim 1, it is characterized in that: The time period load data includes segmented operating power values, segmented ambient temperature data, and equipment load level grouping information; the task power priority information includes task power allocation values, time period task distribution characteristics, and task priority sorting data; the balanced load distribution value includes regional load distribution ratios, inter-regional load balancing results, and segmented load distribution adjustment data; the abnormal fluctuation feature table includes load fluctuation amplitude characteristics, abnormal time segment data, and abnormal point offset feature information; the equipment linkage fault impact results include equipment linkage dependency, inter-equipment linkage strength relationship, and linkage fault sorting data; the control signal optimization results include adjusted signal allocation rules, optimized time allocation tables, and inter-equipment signal linkage relationship tables.

3. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The operation status monitoring module includes a data acquisition submodule, a time marking and grouping submodule, and a load data sorting submodule; The data acquisition submodule is based on the energy-consuming equipment in the park. Through the operating power sensor and the ambient temperature sensor, the operating power value and ambient temperature data of each energy-consuming equipment are collected to obtain the operating power and ambient data set; The time marking and grouping submodule associates the data timestamp based on the operating power and environment data set, reads the timestamp field in the data, compares it with the standard time index, groups the data according to the time dimension, and obtains the time series marking and grouping data; The load data sorting submodule calculates based on the time series annotation and grouping data according to the load level of the energy-consuming equipment, divides it into time periods, determines the peak and average of the operating power in the data, and obtains the load data for each time period.

4. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The energy consumption distribution analysis module includes a power data acquisition submodule, a power distribution characteristic analysis submodule, and a task power sorting submodule; The power data acquisition submodule is based on the load data in each period, and the operating power value and time distribution data of the energy-consuming equipment collected by the IoT terminal, combined with the identification information of the energy-consuming equipment, identifies key feature points, including power peak value, valley value and stable interval, to obtain power time distribution data; The power distribution characteristic analysis submodule analyzes the power value and time distribution data in each time period based on the power time distribution data, calculates the cumulative value of the operating power in chronological order, and then performs distribution characteristic statistics on multiple segments of data in combination with time tags to obtain power distribution characteristic information; The task power sorting submodule determines the power distribution characteristic data in the task window based on the power distribution characteristic information, compares the operating power demand and time period distribution according to the task priority, adjusts the time period sequence and power distribution, and obtains the task power priority information.

5. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 4 is characterized in that: The identification information of the energy-consuming equipment is combined to check the integrity of the operating power value and time distribution data record, according to the formula: ； Calculate the operating power value integrity determination index I; in, Represents the measured power value of the energy-consuming device collected by the IoT terminal in time period t, Represents the reference operating power value of the energy-consuming equipment, represents the smoothness coefficient of power distribution within the time period, and Respectively represent the starting point and ending point of the time distribution of the power recording data, represents the total number of time points in the period, It is the time unit of integration and defines the continuity of the integral calculation.

6. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The regional load optimization module includes a segment load statistics submodule, a regional load distribution submodule, and a load balancing comparison submodule; The segment load statistics submodule analyzes the segment load data according to the time division based on the task power priority information and the segment load data in the task window, calculates the ratio of each segment operation power, determines the proportional relationship of the segment load, and obtains the segment load ratio data; The regional load distribution submodule identifies the distribution node data of each region based on the segment load ratio data and the regional node distribution of the Internet of Things, compares the segment load ratio with the regional node capacity, calculates the redistributed load value node by node, and classifies the segment load value by region to obtain the regional distribution load value; The load balancing comparison submodule allocates load values ​​based on the area, analyzes regional resource distribution and task requirements, groups and calculates the load values ​​of the area, determines unbalanced nodes with regional load differences based on the load values, adjusts the node load relationship, and obtains a balanced load distribution value.

7. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 6 is characterized in that: The above comparison of the segment load ratio and the regional node capacity is used to calculate the redistributed load value node by node, according to the formula: ； Calculate the redistributed load value for each node ; in, Representative Node The original segment load value, Representative Node The capacity, Represents the number of all nodes in the region, Represents the number of all nodes in the segment load data.

8. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The energy consumption abnormality monitoring module includes a load fluctuation monitoring submodule, an abnormal power determination submodule, and a fluctuation characteristic statistics submodule; The load fluctuation monitoring submodule monitors the change data of each period in sections based on the balanced load distribution value, identifies the load change point, and classifies the time position and power difference of the change point to obtain the load fluctuation point information; The abnormal power determination submodule analyzes the amplitude and offset range of power fluctuation based on the load fluctuation point information, compares the fluctuation amplitude value with the offset range limit, and screens abnormal data to obtain abnormal fluctuation point information; The fluctuation feature statistics submodule identifies the power offset value within the time range based on the abnormal fluctuation point information, the offset amplitude and time range of the abnormal fluctuation point, and analyzes the fluctuation features in each segment to obtain an abnormal fluctuation feature table.

9. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The fault association module includes a load linkage identification submodule, an equipment correlation calculation submodule, and a linkage impact sorting submodule; The load linkage identification submodule calculates the fluctuation frequency in the time series based on the abnormal fluctuation feature table, compares the load changes of multiple energy-consuming devices, identifies the corresponding relationship between the time point and the fluctuation amplitude, marks the linkage features of the energy-consuming devices, and obtains the device linkage data; The device correlation calculation submodule analyzes the load linkage relationship of the energy-consuming equipment based on the device linkage data, calculates the dependency value of the load change value of the energy-consuming equipment and the linkage time, and obtains the device correlation strength value; The linkage impact sorting submodule sorts the impact values ​​based on the equipment association strength value and the impact values ​​of the linkage relationship of the energy-consuming equipment in combination with the sorting rules, adjusts the association order of the energy-consuming equipment, filters the conflicting impact values, and obtains the equipment linkage fault impact result.

10. The energy-saving control system for energy-consuming equipment in a park based on the Internet of Things technology according to claim 1 is characterized in that: The signal feedback optimization module includes a load adjustment value extraction submodule, a linkage relationship verification submodule, and a signal optimization calculation submodule; The load adjustment value extraction submodule analyzes the corresponding rules between the load adjustment value and the linkage relationship based on the equipment linkage fault impact result, analyzes the linkage correlation and state fluctuation amplitude between the equipment, determines the linkage equipment relationship corresponding to the adjustment value, and obtains the load adjustment relationship data; The linkage relationship verification submodule verifies the dependency between the adjustment value and the device linkage relationship based on the load adjustment relationship data, extracts the conflict points of the device linkage, analyzes the time dependency value and the linkage relationship of the conflict point, marks the conflict characteristics, and re-associates the adjustment value with the linkage relationship to obtain the adjustment conflict dependency characteristic result; The signal optimization calculation submodule adjusts the signal and time allocation data based on the adjustment conflict dependency characteristic results, combines the time interval of the adjustment signal with the device priority, analyzes the mutual influence of the time sequence and the interactive regulation between devices, recalculates and reconstructs the signal time series, and obtains the control signal optimization result.

Images